IBM Platform Computing

HPC Cloud

The benefits of cloud computing are well-known – efficiency, flexibility, high utilization – but have been difficult to achieve in HPC environments. IBM Platform Computing solutions for HPC Cloud are designed to deliver high performance cloud resources that provide the performance you need along with the advantages of the cloud model.

The Challenge

The extraordinary performance demands that engineering, scientific, financial, and research workloads place upon technical and high performance computing (HPC) infrastructure has historically meant that these workloads were not suitable for cloud deployments, especially those that use virtualization technology. However, the performance gap between physical and virtual deployments is now closing and HPC and technical computing users can now benefit from the flexibility, cost efficiencies and improved resource sharing that cloud provides.

The Solution

Faster answers, fewer new costs

Cloud technologies, when carefully and flexibly applied, maximize the advantages and minimize the disadvantages for HPC. The packaging and automation of these cloud technologies is the value IBM Platform Computing Cloud solutions provide.

IBM Platform Computing solutions for HPC Cloud are designed to transform static computing resources into flexible high performance clouds that can be shared, remotely managed and easily provisioned to support the demands of compute- and data-intensive workloads and changing user requirements. This means your organization can deploy an efficient, consolidated infrastructure that meets time variant business and research demands—and also offers the performance that your users demand.

Based on proven cluster, grid, and HPC cloud technology from IBM Platform Computing, these cloud offerings have intuitive and versatile user interfaces, automated workload-based virtual and physical machine provisioning, robust “resource-aware” job scheduling and migration, and powerful self-service deployment capabilities to help ensure departmental, enterprise or community resources are optimally distributed and easy to manage. The tools are designed so you can align resources with project priorities and realize improved operational and cost efficiencies while achieving business goals unattainable with other management systems.

The Benefits

By applying cloud technologies and standards to established Technical Computing and HPC infrastructures, costly, inflexible silos can be eliminated and shared computing resources can be fully utilized to help you:

• Enhance productivity and facilitate collaboration with an easy-to-use, web-based portal and visualization tools.
• Improve data access, resource availability and security while boosting performance.
• Increase throughput of heterogeneous workloads across diverse resources.
• Increase automation and decrease manual effort for improved administrator productivity.
• Reduce operating costs and total cost of ownership with a consolidated high-performance infrastructure.

The Specifics

IBM Platform Computing provides a comprehensive set of cloud management capabilities; all designed to work together to address your HPC cloud needs.

Workload management

• IBM® Platform™ LSF is a powerful workload management platform for demanding, distributed HPC environments. It provides a comprehensive set of intelligent, policy-driven scheduling features that enable you to utilize all of your compute infrastructure resources and ensure optimal application performance.
• IBM® Platform™ HPC is a complete high performance computing management solution in a single product. It includes a range of out-of the-box features designed to help reduce the complexity of your HPC environment and improving your time-to-solution.
• IBM® Platform™ Symphony software delivers powerful enterprise-class management for running compute and data intensive distributed applications on a scalable, shared grid. It accelerates dozens of parallel applications, for faster results and better utilization of all available resources.

Automated cloud provisioning and workload migration

• IBM® Platform™ Dynamic Cluster turns static IBM Platform LSF clusters into dynamic cloud infrastructure. By automatically changing the composition of clusters to meet ever-changing workload demands, service levels are improved and organizations can do more work with less infrastructure.

Shared infrastructure, multiple clusters and tenants, self-serve cluster creation

• IBM® Platform™ Cluster Manager - Advanced Edition enables self-service creation and management of multiple flexible clusters to deliver the performance required by the compute-intensive workloads in multitenant high performance computing (HPC) environments. Platform Cluster Manager consolidates disparate cluster infrastructures of technical computing and analytics workloads, and provides one centralized interface to simplify infrastructure management.

Graphical job submission and process flow management

• IBM® Platform™ Application Center provides a flexible, easy to use interface for cluster users and administrators. Available as an add-on module to IBM Platform LSF, Platform Application Center enables users to interact with intuitive, self-documenting standardized interfaces.
• IBM® Platform™ Process Manager enables users to design computational processes, capturing and protecting repeatable best practices. Workflow steps and dependencies are documented using an intuitive graphical interface, enabling users to automate lengthy, repetitive tasks that are prone to human error.